commit fb0eb99ffcca02667a73a2a440f391173206227a Author: George Kadianakis desnacked@riseup.net Date: Fri Jun 15 18:49:35 2012 +0300

Display country names instead of country codes. --- task-2718/country_info.py | 251 +++++++++++++++++++++++++++++++++++++++++++++ task-2718/detector.py | 19 +++- 2 files changed, 266 insertions(+), 4 deletions(-)

diff --git a/task-2718/country_info.py b/task-2718/country_info.py new file mode 100644 index 0000000..9dbdeb5 --- /dev/null +++ b/task-2718/country_info.py @@ -0,0 +1,251 @@ +# -*- coding: utf-8 -*- + +countries = { + "ad" : "Andorra", + "ae" : "the United Arab Emirates", + "af" : "Afghanistan", + "ag" : "Antigua and Barbuda", + "ai" : "Anguilla", + "al" : "Albania", + "am" : "Armenia", + "an" : "the Netherlands Antilles", + "ao" : "Angola", + "aq" : "Antarctica", + "ar" : "Argentina", + "as" : "American Samoa", + "at" : "Austria", + "au" : "Australia", + "aw" : "Aruba", + "ax" : "the Aland Islands", + "az" : "Azerbaijan", + "ba" : "Bosnia and Herzegovina", + "bb" : "Barbados", + "bd" : "Bangladesh", + "be" : "Belgium", + "bf" : "Burkina Faso", + "bg" : "Bulgaria", + "bh" : "Bahrain", + "bi" : "Burundi", + "bj" : "Benin", + "bl" : "Saint Bartelemey", + "bm" : "Bermuda", + "bn" : "Brunei", + "bo" : "Bolivia", + "br" : "Brazil", + "bs" : "the Bahamas", + "bt" : "Bhutan", + "bv" : "the Bouvet Island", + "bw" : "Botswana", + "by" : "Belarus", + "bz" : "Belize", + "ca" : "Canada", + "cc" : "the Cocos (Keeling) Islands", + "cd" : "the Democratic Republic of the Congo", + "cf" : "Central African Republic", + "cg" : "Congo", + "ch" : "Switzerland", + "ci" : u"Côte d'Ivoire", + "ck" : "the Cook Islands", + "cl" : "Chile", + "cm" : "Cameroon", + "cn" : "China", + "co" : "Colombia", + "cr" : "Costa Rica", + "cu" : "Cuba", + "cv" : "Cape Verde", + "cx" : "the Christmas Island", + "cy" : "Cyprus", + "cz" : "the Czech Republic", + "de" : "Germany", + "dj" : "Djibouti", + "dk" : "Denmark", + "dm" : "Dominica", + "do" : "the Dominican Republic", + "dz" : "Algeria", + "ec" : "Ecuador", + "ee" : "Estonia", + "eg" : "Egypt", + "eh" : "the Western Sahara", + "er" : "Eritrea", + "es" : "Spain", + "et" : "Ethiopia", + "fi" : "Finland", + "fj" : "Fiji", + "fk" : "the Falkland Islands (Malvinas)", + "fm" : "the Federated States of Micronesia", + "fo" : "the Faroe Islands", + "fr" : "France", + "fx" : "Metropolitan France", + "ga" : "Gabon", + "gb" : "the United Kingdom", + "gd" : "Grenada", + "ge" : "Georgia", + "gf" : "French Guiana", + "gg" : "Guernsey", + "gh" : "Ghana", + "gi" : "Gibraltar", + "gl" : "Greenland", + "gm" : "Gambia", + "gn" : "Guinea", + "gp" : "Guadeloupe", + "gq" : "Equatorial Guinea", + "gr" : "Greece", + "gs" : "South Georgia and the South Sandwich Islands", + "gt" : "Guatemala", + "gu" : "Guam", + "gw" : "Guinea-Bissau", + "gy" : "Guyana", + "hk" : "Hong Kong", + "hm" : "Heard Island and McDonald Islands", + "hn" : "Honduras", + "hr" : "Croatia", + "ht" : "Haiti", + "hu" : "Hungary", + "id" : "Indonesia", + "ie" : "Ireland", + "il" : "Israel", + "im" : "the Isle of Man", + "in" : "India", + "io" : "the British Indian Ocean Territory", + "iq" : "Iraq", + "ir" : "Iran", + "is" : "Iceland", + "it" : "Italy", + "je" : "Jersey", + "jm" : "Jamaica", + "jo" : "Jordan", + "jp" : "Japan", + "ke" : "Kenya", + "kg" : "Kyrgyzstan", + "kh" : "Cambodia", + "ki" : "Kiribati", + "km" : "Comoros", + "kn" : "Saint Kitts and Nevis", + "kp" : "North Korea", + "kr" : "the Republic of Korea", + "kw" : "Kuwait", + "ky" : "the Cayman Islands", + "kz" : "Kazakhstan", + "la" : "Laos", + "lb" : "Lebanon", + "lc" : "Saint Lucia", + "li" : "Liechtenstein", + "lk" : "Sri Lanka", + "lr" : "Liberia", + "ls" : "Lesotho", + "lt" : "Lithuania", + "lu" : "Luxembourg", + "lv" : "Latvia", + "ly" : "Libya", + "ma" : "Morocco", + "mc" : "Monaco", + "md" : "the Republic of Moldova", + "me" : "Montenegro", + "mf" : "Saint Martin", + "mg" : "Madagascar", + "mh" : "the Marshall Islands", + "mk" : "Macedonia", + "ml" : "Mali", + "mm" : "Burma", + "mn" : "Mongolia", + "mo" : "Macau", + "mp" : "the Northern Mariana Islands", + "mq" : "Martinique", + "mr" : "Mauritania", + "ms" : "Montserrat", + "mt" : "Malta", + "mu" : "Mauritius", + "mv" : "the Maldives", + "mw" : "Malawi", + "mx" : "Mexico", + "my" : "Malaysia", + "mz" : "Mozambique", + "na" : "Namibia", + "nc" : "New Caledonia", + "ne" : "Niger", + "nf" : "Norfolk Island", + "ng" : "Nigeria", + "ni" : "Nicaragua", + "nl" : "the Netherlands", + "no" : "Norway", + "np" : "Nepal", + "nr" : "Nauru", + "nu" : "Niue", + "nz" : "New Zealand", + "om" : "Oman", + "pa" : "Panama", + "pe" : "Peru", + "pf" : "French Polynesia", + "pg" : "Papua New Guinea", + "ph" : "the Philippines", + "pk" : "Pakistan", + "pl" : "Poland", + "pm" : "Saint Pierre and Miquelon", + "pn" : "the Pitcairn Islands", + "pr" : "Puerto Rico", + "ps" : "the Palestinian Territory", + "pt" : "Portugal", + "pw" : "Palau", + "py" : "Paraguay", + "qa" : "Qatar", + "re" : "Reunion", + "ro" : "Romania", + "rs" : "Serbia", + "ru" : "Russia", + "rw" : "Rwanda", + "sa" : "Saudi Arabia", + "sb" : "the Solomon Islands", + "sc" : "the Seychelles", + "sd" : "Sudan", + "se" : "Sweden", + "sg" : "Singapore", + "sh" : "Saint Helena", + "si" : "Slovenia", + "sj" : "Svalbard and Jan Mayen", + "sk" : "Slovakia", + "sl" : "Sierra Leone", + "sm" : "San Marino", + "sn" : "Senegal", + "so" : "Somalia", + "sr" : "Suriname", + "st" : u"São Tomé and Príncipe", + "sv" : "El Salvador", + "sy" : "the Syrian Arab Republic", + "sz" : "Swaziland", + "tc" : "Turks and Caicos Islands", + "td" : "Chad", + "tf" : "the French Southern Territories", + "tg" : "Togo", + "th" : "Thailand", + "tj" : "Tajikistan", + "tk" : "Tokelau", + "tl" : "East Timor", + "tm" : "Turkmenistan", + "tn" : "Tunisia", + "to" : "Tonga", + "tr" : "Turkey", + "tt" : "Trinidad and Tobago", + "tv" : "Tuvalu", + "tw" : "Taiwan", + "tz" : "the United Republic of Tanzania", + "ua" : "Ukraine", + "ug" : "Uganda", + "um" : "the United States Minor Outlying Islands", + "us" : "the United States", + "uy" : "Uruguay", + "uz" : "Uzbekistan", + "va" : "Vatican City", + "vc" : "Saint Vincent and the Grenadines", + "ve" : "Venezuela", + "vg" : "the British Virgin Islands", + "vi" : "the United States Virgin Islands", + "vn" : "Vietnam", + "vu" : "Vanuatu", + "wf" : "Wallis and Futuna", + "ws" : "Samoa", + "ye" : "Yemen", + "yt" : "Mayotte", + "za" : "South Africa", + "zm" : "Zambia", + "zw" : "Zimbabwe" + } diff --git a/task-2718/detector.py b/task-2718/detector.py index 5a55b39..9fa5584 100644 --- a/task-2718/detector.py +++ b/task-2718/detector.py @@ -54,8 +54,19 @@ from datetime import date from datetime import timedelta import os.path

+# Country code -> Country names +import country_info + +# write utf8 to file +import codecs + days = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"]

+def get_country_name_from_cc(country_code): + if (country_code.lower() in country_info.countries): + return country_info.countries[country_code.lower()] + return country_code # if we didn't find the cc in our map + """ Represents a .csv file containing information on the number of connecting Tor users per country. @@ -352,7 +363,7 @@ def write_ml_report(tss, minx, maxx, INTERV, DAYS, notification_period=None): if notification_period is None: notification_period = DAYS

- report_file = open('short_censorship_report.txt', 'w') + report_file = codecs.open('short_censorship_report.txt', 'w', 'utf-8') file_prologue_written = False

s = tss.get_largest(None) # no restrictions, get 'em all. @@ -363,7 +374,7 @@ def write_ml_report(tss, minx, maxx, INTERV, DAYS, notification_period=None): scores.sort() scores.reverse()

- for downscores,users_n,upscores,country_name in scores: + for downscores,users_n,upscores,country_code in scores: if (downscores > 0) or (upscores > 0): if not file_prologue_written: prologue = "=======================\n" @@ -374,10 +385,10 @@ def write_ml_report(tss, minx, maxx, INTERV, DAYS, notification_period=None):

if ((upscores > 0) and (downscores == 0)): s = "We detected an unusual spike of Tor users in %s (%d upscores, %d users).\n" % \ - (country_name, upscores, users_n) + (get_country_name_from_cc(country_code), upscores, users_n) else: s = "We detected %d potential censorship events in %s (users: %d, upscores: %d).\n" % \ - (downscores, country_name, users_n, upscores) + (downscores, get_country_name_from_cc(country_code), users_n, upscores)

report_file.write(s + "\n")